He, Yulan and Young, S.
(2003).
Hidden vector state model for hierarchical semantic parsing.
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference, 1
pp. 268–271.
Full text available as:
|
Due to copyright restrictions, this file is not available for public download
|
Abstract
The paper presents a hidden vector state (HVS) model for hierarchical semantic parsing. The model associates each state of push-down automata with the state of an HMM. State transitions are factored into separate stack pop and push operations and then constrained to give a tractable search space. The result is a model which is complex enough to capture hierarchical structure but which can be trained automatically from unannotated data. Experiments have been conducted on ATIS-3 1993 and 1994 test sets. The results show that the HVS model outperforms a general finite state tagger (FST) by 19% to 32% in error reduction.
| Item Type: |
Journal Article
|
| Copyright Holders: |
2003 IEEE |
| ISSN: |
1520-6149 |
| Keywords: |
HMM; error reduction; general finite state tagger; hidden vector state model; hierarchical semantic parsing; push-down automata; search space; speech recognition; spoken dialogue systems; stack pop operations; stack push operations |
| Academic Unit/Department: |
Knowledge Media Institute |
| Interdisciplinary Research Centre: |
Centre for Research in Computing (CRC) |
| Item ID: |
23778 |
| Depositing User: |
Kay Dave
|
| Date Deposited: |
29 Mar 2011 10:31 |
| Last Modified: |
28 Oct 2012 07:46 |
| URI: |
http://oro.open.ac.uk/id/eprint/23778 |
Actions (login may be required)
